© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 358
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "it" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the pronoun "It" indicating a subject in a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    it was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᴗ
    -0.46
     содержа
    -0.46
    прочем
    -0.45
    레
    -0.45
    amid
    -0.44
     propósito
    -0.43
    ほら
    -0.43
    arean
    -0.43
    metingen
    -0.43
     này
    -0.43
    POSITIVE LOGITS
     '\\;'
    0.81
    NameInMap
    0.81
    TagMode
    0.77
    AddHtmlAttribute
    0.76
     initComponents
    0.74
    expandindo
    0.74
    ंदीखरीदारी
    0.73
     оригіналу
    0.73
    verwijspagina
    0.72
     GenerationType
    0.69
    Activations Density 0.041%

    No Known Activations